Struct Model 

pub struct Model {
    pub id: String,
    pub name: Option<String>,
    pub description: Option<String>,
    pub type: Option<String>,
    pub created_at: Option<u64>,
    pub owned_by: Option<String>,
    pub context_length: Option<u32>,
    pub max_output_tokens: Option<u32>,
}

Represents a single model available from a provider.

This struct is designed to be flexible enough to accommodate the varying responses from different LLM providers while providing a common interface.

Fields

• id: The unique identifier for the model (required)
• name: A human-readable name for the model
• description: A detailed description of the model’s capabilities
• r#type: The type of model (e.g., “chat”, “completion”, “embedding”)
• created_at: Timestamp when the model was created
• owned_by: The organization or entity that owns the model
• context_length: The maximum context window size for the model
• max_output_tokens: The maximum tokens the model may generate per response

Example

use rig_core::model::Model;

// Create a model with just an ID
let model = Model::from_id("gpt-4");

// Create a model with ID and name
let model = Model::new("gpt-4", "GPT-4");

// Create a model with all fields
let model = Model {
    id: "gpt-4".to_string(),
    name: Some("GPT-4".to_string()),
    description: Some("A large language model...".to_string()),
    r#type: Some("chat".to_string()),
    created_at: Some(1677610600),
    owned_by: Some("openai".to_string()),
    context_length: Some(8192),
    max_output_tokens: Some(4096),
};

Fields

id: String

The unique identifier for the model (required)

name: Option<String>

A human-readable name for the model

description: Option<String>

A detailed description of the model’s capabilities

type: Option<String>

The type of model (e.g., “chat”, “completion”, “embedding”)

created_at: Option<u64>

Timestamp when the model was created (Unix epoch)

owned_by: Option<String>

The organization or entity that owns the model

context_length: Option<u32>

The maximum context window size for the model

max_output_tokens: Option<u32>

The maximum number of tokens the model may generate in one response.

Distinct from Self::context_length: that is the input window, this is the output ceiling, and for most models the output ceiling is far smaller (Gemini 2.5 Flash: 1,048,576 in, 65,536 out).

None means the provider’s listing does not report one — never a default rig invented. Rig does not send this value on requests: omitting an output limit lets the provider apply its own per-model default, and populating it from here would reintroduce a rig-chosen cap by another route (rig#2322). It is for callers and diagnostics.

Implementations

impl Model

pub fn new(id: impl Into<String>, name: impl Into<String>) -> Model

Creates a new Model with the given ID and name.

Arguments

• id - The unique identifier for the model
• name - A human-readable name for the model

Example

use rig_core::model::Model;

let model = Model::new("gpt-4", "GPT-4");
assert_eq!(model.id, "gpt-4");
assert_eq!(model.name, Some("GPT-4".to_string()));

pub fn from_id(id: impl Into<String>) -> Model

Creates a new Model with only the required ID field.

Arguments

• id - The unique identifier for the model

Example

use rig_core::model::Model;

let model = Model::from_id("gpt-4");
assert_eq!(model.id, "gpt-4");
assert_eq!(model.name, None);

pub fn display_name(&self) -> &str

Returns a reference to the model’s name, or the ID if no name is set.

This is useful for display purposes when you want to show the most human-readable identifier available.

Example

use rig_core::model::Model;

let model_with_name = Model::new("gpt-4", "GPT-4");
assert_eq!(model_with_name.display_name(), "GPT-4");

let model_without_name = Model::from_id("gpt-4");
assert_eq!(model_without_name.display_name(), "gpt-4");

Trait Implementations

impl Clone for Model

fn clone(&self) -> Model

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Model

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Model

fn deserialize<__D>( __deserializer: __D, ) -> Result<Model, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for Model

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Eq for Model

impl From<GroqModelEntry> for Model

fn from(value: GroqModelEntry) -> Model

Converts to this type from the input type.

impl From<ListModelEntry> for Model

fn from(value: ListModelEntry) -> Model

Converts to this type from the input type.

impl From<ListModelEntry> for Model

fn from(value: ListModelEntry) -> Model

Converts to this type from the input type.

impl From<ListModelEntry> for Model

fn from(value: ListModelEntry) -> Model

Converts to this type from the input type.

impl From<ListModelEntry> for Model

fn from(value: ListModelEntry) -> Model

Converts to this type from the input type.

impl From<ListModelEntry> for Model

fn from(value: ListModelEntry) -> Model

Converts to this type from the input type.

impl From<MistralModelEntry> for Model

fn from(value: MistralModelEntry) -> Model

Converts to this type from the input type.

impl From<ModelEntry> for Model

fn from(value: ModelEntry) -> Model

Converts to this type from the input type.

impl PartialEq for Model

fn eq(&self, other: &Model) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for Model

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Model

impl TryFrom<ListModelEntry> for Model

type Error = MissingModelIdError

The type returned in the event of a conversion error.

fn try_from( value: ListModelEntry, ) -> Result<Model, <Model as TryFrom<ListModelEntry>>::Error>

Performs the conversion.